Counting eosinophils in bronchoalveolar lavage fluid images with fuzzy methodology

This paper proposes a new fuzzy approach to count eosinophils, as a measure of inflammation, in bronchoalveolar lavage fluid images, provided by digital camera through microscope. We use fuzzy cluster analysis and fuzzy classification algorithm to determine the number of objects in an image. For this purpose, a fuzzy image processing procedure consisting of five main stages is presented. The first stage is pre-highlighting the objects in the images by using an image pre-processing method for enhancement, which is sharpening the image with the Laplaian high pass filter in order to have acceptable contrast in the image. The second stage is segmentation by clustering with fuzzy c-mean algorithm for portioning. In this stage the clustered data are the rough symbols of objects in the image containing noise. In the third step, first, a Gaussian low pass filter is used for noise reduction. Then, a contrast adoption in the image is done by modifying the membership functions in the image [H.R. Tizhoosh, G. Krell, B. Michaelis, Knowledge-based enhancement of megavoltage images in radiation therapy using a hybrid neuro-fuzzy system, Image and Vision Computing 19(July) (2000) 217–233]. Object recognition, the fourth stage, will be done by using fuzzy labeling for the objects in the image, using a fuzzy classification method. The number of labeled images shows the number of eosinophils in an image which is an index for diagnosing inflammation. The last stage is tuning parameters and verification of the system performance by using a feed forward Neural Network.     

A hybrid modeling approach for forecasting the volatility of S&P 500 index return

Forecasting volatility is an essential step in many financial decision makings. GARCH family of models has been extensively used in finance and economics, particularly for estimating volatility. The motivation of this study is to enhance the ability of GARCH models in forecasting the return volatility. We propose two hybrid models based on EGARCH and Artificial Neural Networks to forecast the volatility of S&P 500 index. The estimates of volatility obtained by an EGARCH model are fed forward to a Neural Network. The input to the first hybrid model is complemented by historical values of other explanatory variables. The second hybrid model takes as inputs both series of the simulated data and explanatory variables. The forecasts obtained by each of those hybrid models have been compared with those of EGARCH model in terms of closeness to the realized volatility. The computational results demonstrate that the second hybrid model provides better volatility forecasts.     

Efficient loading and entrapment of tamoxifen in human serum albumin based nanoparticulate delivery system by a modified desolvation technique

Herein, the poorly water-soluble drug, Tamoxifen (Tmx), was loaded in the amphipathic matrix of human serum albumin (HSA) nanoparticles by a modified desolvation method. In order to enhance the drug loading (DL) and drug entrapment efficiency (DEE) (<2% and 10%, respectively), ultrasonication of Tmx-HSA mixture was performed prior to desolvation process. Tmx loading and entrapment efficiency were optimized by employment of the response surface methodology (RSM)-central composite design (CCD) of experiments. Under the optimum conditions of 1.59 mg Tmx/ml concentration, 7.76 pH and 5 h incubation of HSA-Tmx, the DL of 6.7% and DEE of 74% are achievable. Particles with the average size of 195 nm, zeta potential of −21 mV and polydispersity index of 0.09 were produced under these conditions. A more sustained Tmx release behavior was observed from polyethylene glycol (PEG) conjugated nanoparticles in comparison to the non-PEGylated ones. The short-term stability investigation showed no alteration in physicochemical properties of nanoparticles at 4 and 37 °C, but small increase in nanoparticles size was observed after three months of storage at room temperature. This is the first report for efficient production of a Tmx delivery system based on HSA nanoparticles.     

Curcumin and Liver Disease: from Chemistry to Medicine

Curcumin, the natural yellow‐colored active principle, also called turmeric yellow, extracted from the perennial herb Curcuma longa L., has potent biological and pharmacological properties such as antioxidant, anti‐inflammatory, antifungal, antibacterial, anti‐ischemic, antitumor, and anticancer actions. The molecular mechanism of the hepatoprotective action of curcumin is due to its antioxidant properties and inhibitory activity against nuclear factor (NF)‐κB that regulates different proinflammatory and profibrotic cytokines. Overall, scientific reports demonstrate that curcumin has high therapeutic ability for treating hepatic disorders. Here is a systematic discussion of the hepatoprotective activity of curcumin and its possible mechanisms of actions.     

Neuro‐Fuzzy Impact Control (NFIC) for Anti‐Personnel (AP) Mines Detection

An explicit impact control scheme is modified as the main control scheme, while an intelligent control method is designed to deal with uncertainties and varying environment parameters in a mechatronics approach to anti‐personnel (AP) mine detection. The device imitates the manual hand‐prodding technique for mine detection. It inserts a bayonet into the soil and models the dynamics of the manipulator and environment parameters, such as stiffness variation in the soil, to control the impact caused by making contact with a stiff object. An adaptive neuro‐fuzzy plus PID controller is employed to switch from a conventional PID controller to neuro‐fuzzy impact control (NFIC) when an impact is detected. The developed control schemes are validated through experimental work.     

Fuzzy Models for Link Prediction in Social Networks

Predicting missing links and links that may occur in the future in social networks is an attention grabbing topic amid the social network analysts. Owing to the relationship between human‐based system and social sciences in this field, granular computing can help us to model the systems more effectively. The present study aims to propose two new similarity indices, based on granular computing approach and fuzzy logic. It also presents a new hybrid model for creating synergy between various link prediction models. Results show that fuzzy system analysis, in comparison with the crisp approach, can make more effective predictions through better expression of network characteristics. The indices are tested on collaboration networks. It is found that the accuracy of predictions is significantly higher than the crisp approach. It can modify the models for computing the strength of the links and/or predicting the evolutions of the social networks.     

A hierarchical stochastic modelling approach for reconstructing lung tumour geometry from 2D CT images

ABSTRACT

Lung cancer is one of the deadliest cancers in both men and women. Nowadays, several methods are used to cure this cancer including surgery and radiotherapy. These methods require prior knowledge about the shape of tumours. This type of knowledge may also help physicians to determine the cancer type. In this paper we propose a novel approach for 3D reconstruction of tumour geometry from a sequence of 2D images. The proposed approach consists of two phases: tumour segmentation from computed tomography (CT) images and 3D shape reconstruction. Segmentation is conducted using snake optimisation and Gustafson–Kessel clustering. For 3D reconstruction, first, we propose a new approach to interpolate some intermediate slices between original slices. Then, the well-known marching cubes algorithm is used for surface reconstruction. Eventually, we smoothen the surface using an explicit fairing algorithm. Experiments show that our new approach can highly improve the quality and the accuracy of the reconstructed tumour shape.     

A hybrid fuzzy-ontology based intelligent system to determine level of severity and treatment recommendation for Benign Prostatic Hyperplasia

This paper deals with application of fuzzy intelligent systems in diagnosing severity level and recommending appropriate therapies for patients having Benign Prostatic Hyperplasia. Such an intelligent system can have remarkable impacts on correct diagnosis of the disease and reducing risk of mortality. This system captures various factors from the patients using two modules. The first module determines severity level of the Benign Prostatic Hyperplasia and the second module, which is a decision making unit, obtains output of the first module accompanied by some external knowledge and makes an appropriate treatment decision based on its ontology model and a fuzzy type-1 system. In order to validate efficiency and accuracy of the developed system, a case study is conducted by 44 participants. Then the results are compared with the recommendations of a panel of experts on the experimental data. Then precision and accuracy of the results were investigated based on a statistical analysis.     

A type-2 fuzzy expert system based on a hybrid inference method for steel industry

In this paper, a novel type-2 fuzzy expert system for prediction the amount of reagents in desulfurization process of a steel industry in Canada is developed. In this model, the new interval type-2 fuzzy c-regression clustering algorithm for structure identification phase of Takagi–Sugeno (T–S) systems is presented. Gaussian Mixture Model is used to generate partition matrix in clustering algorithm. Then, an interval type-2 hybrid fuzzy system, which is the combination of Mamdani and Sugeno method, is proposed. The new hybrid inference system uses fuzzy disjunctive normal forms and fuzzy conjunctive normal forms for aggregation of antecedents. A statistical test, which uses least square method, is implemented in order to select variables. In order to validate our method, we develop three system modeling techniques and compare the results with our proposed interval type-2 fuzzy hybrid expert system. These techniques are multiple regression, type-1 fuzzy expert system, and interval type-2 fuzzy TSK expert system. For tuning parameters of the system, adaptive-network-based fuzzy inference system is used. Finally, neural network is utilized in order to reduce error of the system. The results show that our proposed method has less error and high accuracy.